MEGA Hub
New

MinerU.Chem: A High-Precision System for Optical Chemical Structure and Reaction Recognition

Published on Aug 4cs.CV

Authors

Do you know Haote Yang?You can claim authorship or link another user.Do you know Jiang Wu?You can claim authorship or link another user.Do you know Jingchao Wang?You can claim authorship or link another user.Do you know Xingjian Wei?You can claim authorship or link another user.Do you know Lixin Ma?You can claim authorship or link another user.Do you know Linye Li?You can claim authorship or link another user.Do you know Chen Zhu?You can claim authorship or link another user.Do you know Xiaolong Wu?You can claim authorship or link another user.Do you know Yuheng Lu?You can claim authorship or link another user.Do you know Ziran Zhu?You can claim authorship or link another user.Do you know Junyuan Gao?You can claim authorship or link another user.Do you know Lingli Ge?You can claim authorship or link another user.Do you know Yuan Xu?You can claim authorship or link another user.Do you know Huijie Ao?You can claim authorship or link another user.Do you know QianQian Wu?You can claim authorship or link another user.Do you know Dechen Lin?You can claim authorship or link another user.Do you know Huaiyu Gu?You can claim authorship or link another user.Do you know Lu Chen?You can claim authorship or link another user.Do you know Shengxin Lu?You can claim authorship or link another user.Do you know ShaSha Wang?You can claim authorship or link another user.Do you know Yuanyuan Cao?You can claim authorship or link another user.Do you know Zhejia Yu?You can claim authorship or link another user.Do you know Ruijie Zhang?You can claim authorship or link another user.Do you know Zimai Tian?You can claim authorship or link another user.Do you know Jiaxing Sun?You can claim authorship or link another user.Do you know Yinfan Wang?You can claim authorship or link another user.Do you know Jiahe Song?You can claim authorship or link another user.Do you know Chuang Wang?You can claim authorship or link another user.Do you know Yubin Wang?You can claim authorship or link another user.Do you know Rui Nie?You can claim authorship or link another user.Do you know Hao Zheng?You can claim authorship or link another user.Do you know Bowen Jiang?You can claim authorship or link another user.Do you know Hongbin Lai?You can claim authorship or link another user.Do you know Yifan He?You can claim authorship or link another user.Do you know Chengjin Liu?You can claim authorship or link another user.Do you know Tingting Zhang?You can claim authorship or link another user.Do you know Liqun Wei?You can claim authorship or link another user.Do you know Lijun Wu?You can claim authorship or link another user.Do you know Bin Wang?You can claim authorship or link another user.Do you know Yuqiang Li?You can claim authorship or link another user.Do you know Guangyu Wang?You can claim authorship or link another user.Do you know Wei Li?You can claim authorship or link another user.Do you know Bowen Zhou?You can claim authorship or link another user.Do you know Dahua Lin?You can claim authorship or link another user.Do you know Conghui He?You can claim authorship or link another user.

Abstract

In organic chemistry papers and patents, molecular structures, reaction schemes, and experimental conditions are often presented as molecular structure depictions, reaction diagrams, and complex tables or figures. Such information is difficult for general-purpose document parsing systems to directly convert into machine-readable data. This limits data production for organic chemistry knowledge base construction and for AI for Chemistry tasks such as reaction prediction, retrosynthesis, condition recommendation, molecular property prediction, and drug molecule design. This report introduces MinerU.Chem, a document parsing system for organic chemistry literature integrated into the MinerU online platform. Built on top of MinerU's general document parsing pipeline, MinerU.Chem adds five chemistry-specific modules: chemistry relevance filtering, molecular structure detection, molecule identifier extraction, molecular structure recognition, and reaction scheme parsing. Together, these modules convert organic-chemistry-related image regions in documents into a Molecule Summary List and a Reaction Summary List. For molecular structure recognition, MinerU.Chem uses CARBON (Complex Atomic Representation and Bonding Object Notation) as its core representation. CARBON enables recognition results to preserve both the visual layout of the original image and complex chemical semantics, while supporting the export of standard downstream formats such as MolFile and SMILES. On the SMILES-evaluable subset of MolRecBench-Wild (N=2,392), MinerU.Chem's molecular structure recognition module achieves a SMILES exact-match accuracy of 93.02%, outperforming the best evaluated comparison system, GPT-5.6-Sol (74.87%), by 18.15 percentage points. The system has been integrated into the MinerU online platform and is available at https://mineru.net/OpenSourceTools/Extractor .

Community

00